SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

remove useless and confusing lm_labels line (#3531)

Browse Source
This commit is contained in:
Patrick von Platen
2020-03-31 15:32:25 +02:00
committed by GitHub
parent 42e1e3c67f
commit 55bcae7f25
1 changed files with 0 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
src/transformers/modeling_t5.py
View File

@@ -901,7 +901,6 @@ class T5ForConditionalGeneration(T5PreTrainedModel):
lm_labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`): lm_labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size,)`, `optional`, defaults to :obj:`None`):
Labels for computing the sequence classification/regression loss. Labels for computing the sequence classification/regression loss.
Indices should be in :obj:`[-100, 0, ..., config.vocab_size - 1]`. Indices should be in :obj:`[-100, 0, ..., config.vocab_size - 1]`.
If :obj:`config.num_labels > 1` a classification loss is computed (Cross-Entropy).
All labels set to ``-100`` are ignored (masked), the loss is only All labels set to ``-100`` are ignored (masked), the loss is only
computed for labels in ``[0, ..., config.vocab_size]`` computed for labels in ``[0, ..., config.vocab_size]``